Multidimensional Attention Domain Adaptive Method Incorporating Degradation Prior for Machine Remaining Useful Life Prediction

• Published in: IEEE transactions on industrial informatics Vol. 20; no. 5; pp. 7345 - 7356
• Main Authors: Xie, Shushuai, Cheng, Wei, Nie, Zelin, Xing, Ji, Chen, Xuefeng, Gao, Lin, Xu, Zhao, Zhang, Rongyong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.05.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Artificial neural networks; Attention mechanism; Convolution; Convolutional neural networks; Data integration; Datasets; Degradation; domain adaptation; Employee welfare; Feature extraction; improved long short-term memory network; Life prediction; Mechanical systems; Modular systems; multisource information fusion; Neural networks; Prediction models; Predictive models; Propulsion systems; remaining useful life prediction; Useful life
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2024.3359455

Machinery remaining useful life (RUL) prediction has important guiding significance for prognostics and health management. In order to improve the prediction accuracy of the RUL prediction model under different working conditions, the transfer method on domain adaptation (DA) has achieved preliminary results. However, on the one hand, the existing DA methods mostly use a single vibration signal to predict RUL, resulting in low model robustness. On the other hand, DA methods force transfer without considering the degradation information specific to the target domain, resulting in negative transfer. To solve the above problems, a degradation prior assisted multisource information fusion domain adaptive method is proposed for cross-domain RUL prediction. In this method, the multisource information fusion is realized by introducing the convolution neural network with a multidimensional attention mechanism, and comprehensive degradation features are obtained. Then, the degradation prior information of the target domain is fused with the multisource degradation characteristics in a weak supervision way, so as to retain the unique degradation features of the target domain. Finally, the cross-domain RUL prediction is realized by improved long short-term memory neural network. The performance of the proposed method is verified by the commercial modular aero-propulsion system simulation dataset and nuclear circulating water pump bearing dataset. The results show that the proposed method has better accuracy and generalization ability than the existing methods.